Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Feature Splitting for GPT2-Small
    3. GPT2-Small
    4. Residual Feature Splitting 24576
    5. 8-RES_FS24576-JB
    6. 11280
    Prev
    Next
    INDEX
    Explanations

    expressions related to discussions, opinions, and thoughts

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res_fs24576-jb
    Configuration
    jbloom/GPT2-Small-Feature-Splitting-Experiment-Layer-8/blocks.8.hook_resid_pre_24576
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    24,576
    Data Type
    torch.float32
    Hook Point
    blocks.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Neuron Alignment
    Index
    Value
    % of L₁
    373
    +0.19
    0.9%
    481
    +0.18
    0.8%
    218
    +0.17
    0.8%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    553
    +0.19
    0.03
    218
    +0.18
    0.03
    351
    +0.17
    0.02
    Negative Logits
    eatured
    -0.65
    uvian
    -0.65
     Warehouse
    -0.62
    alach
    -0.57
     Facilities
    -0.56
     themselves
    -0.56
     advertised
    -0.56
     Released
    -0.56
    UTC
    -0.56
     Featured
    -0.56
    POSITIVE LOGITS
     thanking
    0.81
     saying
    0.77
     :)
    0.71
     sob
    0.70
     haha
    0.66
     telling
    0.65
     â̦"
    0.65
    â̦."
    0.64
    asking
    0.64
    â̦"
    0.64
    Activations Density 0.571%

    No Known Activations